US8326006B2 - Method for breast screening in fused mammography - Google Patents

Method for breast screening in fused mammography Download PDF

Info

Publication number
US8326006B2
US8326006B2 US11/632,078 US63207805A US8326006B2 US 8326006 B2 US8326006 B2 US 8326006B2 US 63207805 A US63207805 A US 63207805A US 8326006 B2 US8326006 B2 US 8326006B2
Authority
US
United States
Prior art keywords
imaging
feature
analysis
processing
interest
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US11/632,078
Other languages
English (en)
Other versions
US20100111379A1 (en
Inventor
Jasjit S. Suri
Yajie Sun
Roman Janer
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Gen Probe Inc
Cytyc Corp
Third Wave Technologies Inc
Hologic Inc
Suros Surgical Systems Inc
Biolucent LLC
Cytyc Surgical Products LLC
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to US11/632,078 priority Critical patent/US8326006B2/en
Application filed by Individual filed Critical Individual
Assigned to GOLDMAN SACHS CREDIT PARTNERS L.P. reassignment GOLDMAN SACHS CREDIT PARTNERS L.P. PATENT SECURITY AGREEMENT Assignors: HOLOGIC, INC.
Assigned to GOLDMAN SACHS CREDIT PARTNERS L.P., AS COLLATERAL AGENT reassignment GOLDMAN SACHS CREDIT PARTNERS L.P., AS COLLATERAL AGENT PATENT SECURITY AGREEMENT Assignors: HOLOGIC, INC.
Publication of US20100111379A1 publication Critical patent/US20100111379A1/en
Assigned to DIRECT RADIOGRAPHY CORP., CYTYC SURGICAL PRODUCTS III, INC., CYTYC CORPORATION, CYTYC PRENATAL PRODUCTS CORP., R2 TECHNOLOGY, INC., CYTYC SURGICAL PRODUCTS LIMITED PARTNERSHIP, CYTYC SURGICAL PRODUCTS II LIMITED PARTNERSHIP, THIRD WAVE TECHNOLOGIES, INC., SUROS SURGICAL SYSTEMS, INC., BIOLUCENT, LLC, HOLOGIC, INC. reassignment DIRECT RADIOGRAPHY CORP. TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS Assignors: GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT
Assigned to GOLDMAN SACHS BANK USA reassignment GOLDMAN SACHS BANK USA SECURITY AGREEMENT Assignors: BIOLUCENT, LLC, CYTYC CORPORATION, CYTYC SURGICAL PRODUCTS, LIMITED PARTNERSHIP, GEN-PROBE INCORPORATED, HOLOGIC, INC., SUROS SURGICAL SYSTEMS, INC., THIRD WAVE TECHNOLOGIES, INC.
Publication of US8326006B2 publication Critical patent/US8326006B2/en
Application granted granted Critical
Assigned to HOLOGIC, INC reassignment HOLOGIC, INC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: FISCHER IMAGING CORPORATION
Assigned to GEN-PROBE INCORPORATED, CYTYC CORPORATION, HOLOGIC, INC., THIRD WAVE TECHNOLOGIES, INC., BIOLUCENT, LLC, CYTYC SURGICAL PRODUCTS, LIMITED PARTNERSHIP, SUROS SURGICAL SYSTEMS, INC. reassignment GEN-PROBE INCORPORATED SECURITY INTEREST RELEASE REEL/FRAME 028810/0745 Assignors: GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT
Assigned to BANK OF AMERICA, N.A., AS COLLATERAL AGENT reassignment BANK OF AMERICA, N.A., AS COLLATERAL AGENT SECURITY AGREEMENT Assignors: BIOLUCENT, LLC, CYTYC CORPORATION, CYTYC SURGICAL PRODUCTS, LIMITED PARTNERSHIP, DIRECT RADIOGRAPHY CORP., GEN-PROBE INCORPORATED, GEN-PROBE PRODESSE, INC., HOLOGIC, INC., SUROS SURGICAL SYSTEMS, INC., THIRD WAVE TECHNOLOGIES, INC.
Assigned to GEN-PROBE INCORPORATED, CYTYC CORPORATION, HOLOGIC, INC., THIRD WAVE TECHNOLOGIES, INC., SUROS SURGICAL SYSTEMS, INC., BIOLUCENT, LLC, CYTYC SURGICAL PRODUCTS, LIMITED PARTNERSHIP reassignment GEN-PROBE INCORPORATED CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 035820 FRAME: 0239. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST RELEASE. Assignors: GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT
Assigned to GOLDMAN SACHS BANK USA reassignment GOLDMAN SACHS BANK USA CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 028810 FRAME: 0745. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY AGREEMENT. Assignors: BIOLUCENT, LLC, CYTYC CORPORATION, CYTYC SURGICAL PRODUCTS, LIMITED PARTNERSHIP, GEN-PROBE INCORPORATED, HOLOGIC, INC., SUROS SURGICAL SYSTEMS, INC., THIRD WAVE TECHNOLOGIES, INC.
Active legal-status Critical Current
Adjusted expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
    • A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
    • A61B6/5229—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image
    • A61B6/5247—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image combining images from an ionising-radiation diagnostic technique and a non-ionising radiation diagnostic technique, e.g. X-ray and ultrasound
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
    • A61B6/03—Computed tomography [CT]
    • A61B6/032—Transmission computed tomography [CT]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/44—Constructional features of apparatus for radiation diagnosis
    • A61B6/4417—Constructional features of apparatus for radiation diagnosis related to combined acquisition of different diagnostic modalities
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/50—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications
    • A61B6/502—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment specially adapted for specific body parts; specially adapted for specific clinical applications for diagnosis of breast, i.e. mammography
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
    • A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
    • A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
    • A61B6/5217—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data extracting a diagnostic or physiological parameter from medical diagnostic data
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
    • A61B8/0825—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the breast, e.g. mammography
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/44—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device
    • A61B8/4416—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device related to combined acquisition of different diagnostic modalities, e.g. combination of ultrasound and X-ray acquisitions
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
    • A61B8/5238—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for combining image data of patient, e.g. merging several images from different acquisition modes into one image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/003—Reconstruction from projections, e.g. tomography
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/155—Segmentation; Edge detection involving morphological operators
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/168—Segmentation; Edge detection involving transform domain methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10112—Digital tomosynthesis [DTS]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10116—X-ray image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10132—Ultrasound image
    • G06T2207/10136—3D ultrasound image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20076—Probabilistic image processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20168—Radial search
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30068—Mammography; Breast
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30096—Tumor; Lesion

Definitions

  • Embodiments of the present invention relate generally to breast screening in fused mammography, and more specifically to analyzing a feature of interest by imaging a first region of interest using a first modality and imaging a second region of interest using a second modality, wherein the first and second regions of interest include the feature of interest.
  • MRI magnetic resonance imaging
  • CT computed tomography
  • FIG. 1 and FIG. 2 show one example of a conventional approach of combined medical imaging modalities as disclosed by General Electric Company.
  • the system generates 3-D X-ray volumetric slices using the 3-D tomosynthesis principle (Wu et al.).
  • a second stage involves 3-D ultrasound (US) scanning using a US transducer, which is used to scan on the top of a plastic sheet.
  • the output includes multiple 3-D ultrasound slices.
  • An embodiment of a method for use in medical imaging of a patient includes, with the patient immobilized with respect to an imaging reference frame, acquiring first digital imaging information including a first region of interest using a first imaging modality; processing the first digital imaging information to identify a feature for analysis; and using a second imaging modality to acquire targeted second imaging information for a second region of interest, the second region of interest corresponding to a subset of the first region of interest, wherein the second region of interest includes the feature for analysis.
  • An embodiment of an apparatus for use in medical imaging includes structure for immobilizing a patient with respect to an imaging reference frame; a first imaging system for acquiring first digital imaging information including a first region of interest using a first imaging modality; a processor processing the first digital imaging information using a diagnostic tool to identify a feature of interest; and a second imaging system for acquiring second imaging information using a second imaging modality, the second imaging information corresponding to a second region of interest including the feature for analysis.
  • FIG. 1 and FIG. 2 show one example of a conventional approach of combined medical imaging modalities as disclosed by General Electric Company;
  • FIG. 3 illustrates one exemplary process for breast imaging with combined ultrasound (US) and X-ray imaging
  • FIG. 4 illustrates exemplary images output from the US transducer stage
  • FIG. 5 illustrates an exemplary system in which image data acquisition can be performed in accordance with one embodiment
  • FIG. 6 illustrates an exemplary embodiment of a process carried out by a fused mammography screening system
  • FIG. 7 illustrates an embodiment of a system for fast lesion detection
  • FIG. 8 shows an embodiment of the X-ray scanning system, which is used in both online and offline systems
  • FIG. 9 shows exemplary procedures carried out by the training system shown in FIG. 7 ;
  • FIG. 10 illustrates an exemplary embodiment of a procedure for pre-segmentation based on multi-resolution
  • FIG. 11 illustrates an exemplary embodiment of the process of ROI extraction
  • FIG. 12 illustrates an embodiment of the binarization step shown in FIG. 11 ;
  • FIG. 13 illustrates an embodiment of the process of initialization with radial lines
  • FIG. 14 illustrates exemplary radial line intersection
  • FIG. 15 illustrates an embodiment of the spline fitting process to obtain the accurate boundary of breast-skin segmentation
  • FIG. 16 depicts an embodiment of a process of extracting the Region of Interest (ROI);
  • FIG. 17 is the block diagram illustrating an embodiment of a process of multi-resolution down-sampling
  • FIG. 18 is a block diagram illustrating one embodiment of a process of segmentation
  • FIG. 19 illustrates an embodiment of a process for obtaining localized histograms from the down-sampled images
  • FIG. 20 is the block diagram illustrating an embodiment of a process for obtaining adaptive localized thresholds
  • FIG. 21 is the block diagram illustrating an embodiment of morphological processing
  • FIG. 22 is a block diagram illustrating an embodiment of a process for eliminating isolated small objects
  • FIG. 23 is a block diagram illustrating an embodiment of a feature collection system
  • FIG. 24 is a block diagram illustrating an embodiment of GLCM feature extraction
  • FIG. 25 is a block diagram illustrating an embodiment of Gabor feature extraction
  • FIG. 26 is a block diagram illustrating a process of shape feature extraction
  • FIG. 27 is a block diagram illustrating one embodiment of a process of wavelet feature extraction
  • FIG. 28 is a block diagram of an exemplary embodiment of a classification system
  • FIG. 29 illustrates an embodiment of a process of decision tree construction
  • FIG. 30 depicts an embodiment of an online lesion detection system.
  • CAD computer-aided detection
  • FFDM full field digital mammography
  • US ultrasound
  • time can be critical.
  • a fast CAD method is needed to guide the following ultrasound imaging system to acquire images of the tumor area only. Hence, the method reduces the time of ultrasound imaging.
  • Various embodiments of systems described herein include an off-line development and training system, and a fast on-line classification system.
  • the system is developed and trained offline; e.g., outside of the time-frame of a medical imaging procedure.
  • the training parameters resulting from the training system are then used online to transform the input test images that help in fast lesion detection system.
  • a lesion detection system includes two stages.
  • stage one initial segmentation is performed in a region of interest (ROI).
  • Stage two includes elimination of false positives using training coefficients that are generated from a knowledge database developed in the offline training system.
  • the breast area of a screening mammogram is segmented from the background using a combination of spline fitting and thresholding to preserve the breast-skin boundary.
  • the breast mask is expanded along the boundary to reduce the edge effects. This is defined as the Region of the Interest (ROI).
  • the ROI image is then down sampled by a down-sampling factor (e.g., by four times) to reduce the image memory requirements and search space (e.g., by 16 times).
  • initial segmentation involves thresholding followed by a morphological post-processing.
  • Local adaptive thresholding based on a local histogram is used to improve the segmentation of low-contrast tumors.
  • Initial segmentation is typically performed in the extracted breast areas.
  • the segmented mass candidates includes ground-truth tumors and false positives.
  • stage two a classification method is used to differentiate true positives from false positives.
  • Features and/or measures are extracted from the lesion candidates in order to reduce the occurrence of false positive results. These features can be used to characterize true positives. Since processing time may be critical, a set of features with fast extraction is typically used.
  • Features such as texture and shape are used in some embodiments. Texture features, such as features extracted from the Gray Level Co-occurrence Matrix (GLCM) or the Gabor filters are used. Shapes features extracted from the boundary of the candidate are also important to classify ground-truth tumors from false positives.
  • GLCM Gray Level Co-occurrence Matrix
  • Shapes features extracted from the boundary of the candidate are also important to classify ground-truth tumors from false positives.
  • the online lesion detection system uses the trained classifier parameters on the test mammographic images. This can be used to differentiate unknown mass candidates obtained from the initial segmentation step. Fast feature extraction typically will not take much time, but will eliminate a large number of false positives.
  • Three-dimensional (3-D) breast volumes can be fused with two-dimensional (2-D) projection images to facilitate breast imaging.
  • Two different modalities can be used.
  • a handheld ultrasound can be used in conjunction with X-ray projection images.
  • Embodiments described herein are directed toward fusion of X-ray projection images and 3-D ultrasound images.
  • an ultrasound projection image is computed from a 3-D ultrasound acquired using a customized ultrasound transducer (see, e.g., FIG. 5 below).
  • the ultrasound projection image can be computed using a fan beam projection algorithm as used in 3-D computed tomography (CT) imaging.
  • CT computed tomography
  • the X-ray projection image can be acquired using a scanning machine such as the SenoScan® machine from Fischer Imaging Corporation.
  • Various embodiments include a steering system that includes a software imaging method, which drives ultrasound image acquisition.
  • the software imaging method renders the screening system fast and accurate.
  • overall acquisition time is improved for scanning in fused modality framework.
  • Some embodiments provide for quick generation of diagnostic images of fused modalities.
  • a potential benefit is the ability to provide a better picture of the lesions, their locations, and/or their growth factor (or angiogenesis of breast cancer).
  • an isotropic volume can be generated. Isotropic volume generation can speed the scanning process because second modality scanning does not require scanning of the entire image.
  • Some embodiments of systems provide an integrated ultrasound scanner that enables accurate scanning. Inaccuracies associated with handheld US scanners can be avoided. In these embodiments, the US scanning is automatic in conjunction with the X-ray scanning system.
  • Various embodiments allow for extendibility of the system to a patient database.
  • the system can be trained offline, and training parameter(s) are used for online lesion detection. Therefore, the training can be extended to a patient database offline in the development.
  • the training parameters can be updated for online classification.
  • Embodiments provide for improved lesion detection by using segmentation to obtain initial lesion candidates.
  • Features are used to reduce the likelihood of false positives. Through a supervised training on a large database, a large portion of false positives can be eliminated. Feature extraction reduces the number of false positives.
  • segmentation of faint lesions is improved over conventional approaches.
  • localized adaptive thresholding improves the initial segmentation to obtain lesion candidates. Whereas segmentation based on the global thresholding may miss these lesions, localized thresholding can improve the segmentation of faint lesions.
  • embodiments can include morphological processing, which allows for identification of solid and connected lesion candidates and removal of spurious dots.
  • Processing carried out by certain embodiments includes down-sampling to improve speed performance. Downsampling in a certain range will not degrade CAD performance for mass detection, but can greatly reduces the processing time. For example, if an image is downsampled four times in each direction, the speed can be up to sixteen times.
  • edge-preserving down-sampling is performed with multiresolution. Down-sampling typically involves anti-aliasing and low-pass filtering, which can have a blurring effect, which degrades the edges. Therefore, multiresolution based down-sampling can preserve sharpness of edges.
  • histogram-based thresholding in an automatic and adaptive manner. Because histogram-based thresholding gives automatic adaptive threshold selection, histogram-based thresholding generally improves threshold results when compared to the results from the fixed threshold approaches.
  • breast mask extraction can improve speed and accuracy.
  • Breast area segmentation from the background can reduce the processing area and improve the speed of processing.
  • Breast mask extraction also reduces the inaccuracy that may occur if detection is used in the background.
  • spline fitting is employed to provide better breast-skin boundary extraction.
  • Spline fitting in the narrow band allows for a continuous breast-skin boundary.
  • the extracted boundary is closer to actual breast-skin line.
  • shape and texture e.g., from Gray-level Co-occurrence Matrices (GLCM) and/or Gabor transforms
  • GLCM Gray-level Co-occurrence Matrices
  • Gabor transforms features facilitate reduction of false positive results: Shape and texture features are used in CAD methods to differentiate true lesions from false positives. Boundary shape features can be a powerful tool in eliminating a large portion of false positives.
  • multi-resolution (including wavelet) analysis is used to reduce the impact of effects due to breast and/or lesion size variation.
  • Multi-resolution analysis can handle size variations, and is advantageous since breast area and lesion size varies with different patients.
  • a list of features is maintained for purposes of system training.
  • the collection of features in the training system allows the expansion of a database of lesion candidates.
  • the collection of features is developed offline.
  • a subset of features is used online.
  • the expansion of the database may change the subset of features.
  • New features can be developed and/or updated quickly. Online classification uses updated training parameters.
  • Various embodiments employs a decision tree, which serves as a fast, powerful classification tool.
  • the decision tree can approach an arbitrary class boundary.
  • the decision tree can be trained or preset using a plurality of “if-then” rules.
  • a fast lesion detection system includes a stand-alone computer-aided detection (CAD) system.
  • CAD computer-aided detection
  • a physician has fast online lesion detection capability in real-time.
  • High specificity of unequivocal negative mammogram of one view may prompt the physician to stop taking the other view. This can reduce the pain the patient endures and the X-ray exposure of the patient.
  • Modules can be implemented in software, hardware, firmware or any combination thereof.
  • Software modules can allow for easy development and modification.
  • modules can be used for the stand-alone application, or be integrated into other systems.
  • FIG. 3 illustrates one exemplary process for breast imaging with combined ultrasound (US) and X-ray imaging.
  • the process includes two stages.
  • the first stage employs an X-ray scanning system, which uses 2-D X-ray projection images (as shown in the ellipse in FIG. 3 ).
  • the second stage involves 3-D ultrasound scanning, wherein the ultrasound scanning is done using the ultrasound transducer by moving the transducer beneath the Mylar sheet.
  • the output includes slices in three orthogonal directions: Sagittal, Coronal and Transverse. Exemplary images output from the US transducer stage are shown in FIG. 4 .
  • FIG. 5 illustrates an exemplary system in which image data acquisition can be performed in accordance with one embodiment.
  • This particular embodiment employs two modalities for screening.
  • the breast to be scanned is positioned between the flat breast support and the breast paddle.
  • the X-ray beams penetrate the patient's breast and the attenuation properties are captured at the digital detector.
  • the image can be reconstructed using the digital detector principle.
  • the 3-D ultrasound breast slices are reconstructed.
  • breast slices are only scanned in the lesion area detected by a fast lesion detection system on the X-ray image.
  • FIG. 6 illustrates an exemplary embodiment of a process carried out by a fused mammography screening system.
  • two modalities are used for screening.
  • the breast to be scanned is positioned between the flat breast support and the breast paddle.
  • the X-ray beams penetrate the patient's breast and the attenuation properties are captured at the digital detector.
  • the image is reconstructed using the digital detector principle.
  • FIG. 7 illustrates an embodiment of a system for fast lesion detection.
  • the fast lesion detection system (FLDS) carries out processes in two phases: offline development and training and a fast online system.
  • Phase one is offline system development and the training system.
  • Phase two is real-time online fast lesion detection, which uses the training parameters from the phase one.
  • Offline system involves X-ray image acquisition and the training system. Training parameters obtained from the training system are then used for online lesion detection.
  • the online system includes three modules: an X-ray scanning system, a pre-segmentation based on multi-resolution, and a lesion detection system. Each module is discussed further below with regard to FIGS. 8-10 .
  • FIG. 8 shows an embodiment of the X-ray scanning system, which is used in both online and offline systems.
  • Mammograms of two views are acquired from X-ray scanning machine. They are Medio-lateral Oblique (MLO) view and Cranio-caudal (CC) View.
  • MLO Medio-lateral Oblique
  • CC Cranio-caudal
  • FIG. 9 shows exemplary procedures carried out by the training system shown in FIG. 7 .
  • Online lesion detection uses the training parameters obtained during the offline training.
  • the first stage involves pre-segmentation based on multi-resolution analysis.
  • edge-preserving down-sampling is performed to reduce the processing time to meet the time constraint of FFDM/US system.
  • lesion candidates are obtained through segmentation. There can be a large number of false positives among lesion candidates.
  • Stages three and four are used to eliminate most false positives through a supervised training processing.
  • Stage three is a feature collection system, which defines a list of feature that could be used to separate false positives from true positives obtained from the segmentation step. A list of features is extracted to distinguish true positives from false positives.
  • a classification system is built through training in the stage four. The training parameters from the classification stage will then be used for the online classification of unknown lesion candidates.
  • FIG. 10 An exemplary embodiment of a procedure for pre-segmentation based on multi-resolution is shown in FIG. 10 .
  • the procedure includes extraction of a Region of Interest (ROI) and multi-resolution downsampling. ROI extraction is used to obtain the breast area. The ROI is then down sampled by a factor to reduce the amount of data required to represent the image. In one particular embodiment, the ROI is down-sampled by four times in each direction to reduce the number of data bits in the image by 16 times. Down-sampling can increase the speed of processing.
  • ROI Region of Interest
  • multi-resolution downsampling can increase the speed of processing.
  • FIG. 11 illustrates an exemplary embodiment of the process of ROI extraction.
  • a mammogram is first binarized.
  • a set of radial lines then draws from the chest wall toward skin boundary to obtain the initial boundary.
  • Spline fitting is then used to obtain the segmented breast area and breast mask using the initial boundary as the starting contour.
  • FIGS. 12-14 three steps of ROI extraction process are described in further detail.
  • FIG. 12 illustrates an embodiment of the binarization step shown in FIG. 11 .
  • the binarization is based on the histogram analysis of breast area and background area. Peaks in the histogram are estimated, and then peaks corresponding to the breast area and the background area are selected. A threshold is automatically calculated between two peaks. A binary mask image is obtained after thresholding.
  • FIG. 13 illustrates an embodiment of the process of initialization with radial lines.
  • FIG. 14 illustrates exemplary radial line intersection. Radial lines are drawn from the chest wall toward the skin boundary. From the intersection of radial lines and the binary mask image, an initial contour is obtained. Radial line intersection advantageously provides for fast extraction of the initial contour. The initial contour is then used to find the accurate breast-skin boundary.
  • FIG. 15 illustrates an embodiment of the spline fitting process to obtain the accurate boundary of breast-skin segmentation. From the initial contour, a narrow band is computed along the initial contour as the range for spline fitting. A stable spline found in the original image is the accurate and continuous boundary of the breast-skin. From the boundary, the segmented breast area can be obtained.
  • FIG. 16 depicts an embodiment of a process of extracting the Region of Interest (ROI).
  • the processing steps are performed with respect to the extracted ROI.
  • a minimum rectangle to enclose the segmented breast area is estimated.
  • the estimated minimum rectangle is called a breast mask.
  • the masked rectangular breast region is then expanded along the boundary to reduce the edge effects. This is called the Region of Interest (ROI).
  • ROI Region of Interest
  • FIG. 17 is the block diagram illustrating an embodiment of a process of multi-resolution down-sampling.
  • Down-sampling involves anti-aliasing and low-pass filtering.
  • Low-pass filtering can have a blurring effect, which causes the degradation of edges and sharp corners.
  • Multi-resolution down-sampling advantageously preserves edges.
  • FIG. 18 is a block diagram illustrating one embodiment of a process of segmentation.
  • the process includes adaptive local thresholding, morphological processing and removal of isolated small objects.
  • the adaptive local thresholding based on the localized histogram improves the initial segmentation of breast lesions. Unlike the global thresholding, the adaptive thresholding can allow the detection of lesions of low-contrast.
  • Morphological processing helps to merge neighboring segmented objects and remove the spurious isolated small objects. Morphological processing helps shape the segmented objects and reduce the number of lesion candidates. The final step of small isolated objects will further remove some very obvious false positives. These lesion candidates obtained will then be input to the detection system to reduce the false positives.
  • FIG. 19 illustrates an embodiment of a process for obtaining localized histograms from the down-sampled images.
  • the image is divided into regions.
  • the region size is determined experimentally.
  • a histogram is computed from each region.
  • FIG. 20 is the block diagram illustrating an embodiment of a process for obtaining adaptive localized thresholds. Threshold is adaptive to each region. Therefore, a better segmentation can be obtained with thresholds adapted to the local regions.
  • FIG. 21 is the block diagram illustrating an embodiment of morphological processing. Morphological closing is used to merge the neighboring binary objects. Due to gray level variation, some gray level objects in the image may be broken. Morphological closing can be used to obtain a continuous object. The morphological opening is used to remove spurious small isolated objects in the segmented image.
  • FIG. 22 is a block diagram illustrating an embodiment of a process for eliminating isolated small objects. This step is used to reduce very obvious false positives, which are small isolated objects. In one embodiment a simple technique is used to eliminate a large portion of false positives. If not removed, spurious objects may cause difficulties in the following lesion detection system.
  • FIG. 23 is a block diagram illustrating an embodiment of a feature collection system.
  • the system performs four kinds of feature extraction. Texture feature extraction is performed using Gray Level Co-occurrence Matrix (GLCM) and Gabor filters. Shape features are also extracted to characterize the boundary of true positives from false positives. Wavelet features are used to account for the size variation of lesion candidates. Extracted features can be used later in the process for the training of a decision tree on a known database.
  • GLCM Gray Level Co-occurrence Matrix
  • Wavelet features are used to account for the size variation of lesion candidates. Extracted features can be used later in the process for the training of a decision tree on a known database.
  • FIG. 24 is a block diagram illustrating an embodiment of GLCM feature extraction.
  • the entry (i,j) of the GLCM matrix is computed as a relative frequency of a pair intensities (i,j) at a certain distance and a certain direction.
  • a set of features can be defined to characterize the texture information in the image.
  • the feature defined in the original paper of GLCM by Haralick is used.
  • feature extraction can include Energy, Entropy, Contrast, and/or Correlation.
  • FIG. 25 is a block diagram illustrating an embodiment of Gabor feature extraction.
  • a Gabor filter bank can be obtained, which gives the spatial and frequency localization.
  • the mean and standard deviation of the filtered candidates are computed as Gabor features. These features can be used for texture analysis and blob detection.
  • the scale and orientation parameters determine the number of Gabor filters in the Gabor filter bank.
  • the high and low frequency parameters are used to determine the frequency range of interest in analysis.
  • FIG. 26 is a block diagram illustrating a process of shape feature extraction.
  • Three types of processing are used to obtain shape features.
  • the final set of shape features is directly computed from the boundary to obtain the statistical features. These features can be used to differentiate the true positives from false positives since usually they have different characteristics.
  • FIG. 27 is a block diagram illustrating one embodiment of a process of wavelet feature extraction.
  • Wavelet transformation can allow the multi-resolution analysis to capture the size variations of lesion candidates.
  • a set of statistical features, mean, variance, entropy and skewness, are computed from each decomposition image.
  • FIG. 28 is a block diagram of an exemplary embodiment of a classification system. From extracted features, a Classification and Regression Tree (CART) is built to obtain the training parameters. The training parameters will then be used online for fast detection of breast lesions.
  • CART Classification and Regression Tree
  • FIG. 29 illustrates an embodiment of a process of decision tree construction.
  • a jini index is computed for each feature at a node to find the best feature in the node.
  • a threshold is automatically decided to have binary decision, which generates left and right child nodes.
  • a binary decision tree is built.
  • the binary decision tree classifier is one of most powerful classification tools available. It can approach to arbitrary class boundary. The training parameters obtained from the built decision tree are then used for online test.
  • FIG. 30 depicts an embodiment of an online lesion detection system.
  • the system uses the same feature collection system as shown in the training system.
  • the training parameters are then applied to classify online testing mammograms.
  • the detected lesion is used to guide the ultrasound imaging to obtain a fast and localized 3-D slices of breast in the lesion area.
  • FFDM full-field digital mammography
  • US ultrasound
  • Isotropic volumes can be generated.
  • Fast lesion detection X-ray modality can guide the generation of isotropic volume for US modality in the reduced breast area.
  • Embodiments improve the specificity and sensitivity of the screening. Scanning with the second modality can be guided by the first modality.
  • Embodiments include automatic ultrasound scanning along with the X-ray scanning system.
  • Embodiments provide extensibility to new patient databases since the system training is performed offline and the training parameters are updated online. Segmentation and supervised detection facilitate lesion detection process. Adaptive localized thresholding enhances segmentation of faint lesions. Morphological processing enhances segmentation of lesion candidates are improved because morphological processing enables imaging of connected objects and removal of isolated small objects.
  • Some embodiments employ down-sampling based on multi-resolution, which reduces the processing area and improves the speed of the overall system. Edges are preserved with multi-resolution based down-sampling.
  • the selection of thresholds is automatic and adaptive because threshold selection is based on histogram analysis in the localized windows.
  • fast lesion detection is performed on an extracted region of interest (ROI) only. Thus, the background is processed as a breast area.
  • ROI extracted region of interest
  • Various embodiments employ spline fitting to extract the breast-skin boundary.
  • Features such as texture and shape features are used to differentiate true lesions from false lesions, thereby reducing the number of false positive results.
  • Embodiments employ wavelet based multi-resolution analysis to reduce the effects due to lesion and/or breast size variation.
  • the collection of features can allow the expansion of database without change of the framework.
  • the collection of features can be developed offline, with a subset of features being used for online detection.
  • the expansion of feature database may change the subset of features.
  • Embodiments employ a classification system based on a decision tree.
  • the decision tree can approach an arbitrary boundary to obtain a low misclassification rate.
  • Embodiments of the fast lesion detection system can be used as a stand-alone computer-aided detection (CAD) system.
  • CAD computer-aided detection
  • the fast online lesion detection system can be available at the mammography screening.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biomedical Technology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Pathology (AREA)
  • Biophysics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Optics & Photonics (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Quality & Reliability (AREA)
  • Pulmonology (AREA)
  • Physiology (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)
  • Image Processing (AREA)
US11/632,078 2004-07-09 2005-07-07 Method for breast screening in fused mammography Active 2028-03-22 US8326006B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US11/632,078 US8326006B2 (en) 2004-07-09 2005-07-07 Method for breast screening in fused mammography

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US58685004P 2004-07-09 2004-07-09
US11/632,078 US8326006B2 (en) 2004-07-09 2005-07-07 Method for breast screening in fused mammography
PCT/US2005/023998 WO2006017101A1 (en) 2004-07-09 2005-07-07 Method for breast screening in fused mammography

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2005/023998 A-371-Of-International WO2006017101A1 (en) 2004-07-09 2005-07-07 Method for breast screening in fused mammography

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US13/694,836 Continuation US9504436B2 (en) 2004-07-09 2012-11-30 Method for breast screening in fused mammography

Publications (2)

Publication Number Publication Date
US20100111379A1 US20100111379A1 (en) 2010-05-06
US8326006B2 true US8326006B2 (en) 2012-12-04

Family

ID=35839570

Family Applications (4)

Application Number Title Priority Date Filing Date
US11/632,078 Active 2028-03-22 US8326006B2 (en) 2004-07-09 2005-07-07 Method for breast screening in fused mammography
US13/694,836 Active US9504436B2 (en) 2004-07-09 2012-11-30 Method for breast screening in fused mammography
US15/359,903 Active US10363010B2 (en) 2004-07-09 2016-11-23 Method for breast screening in fused mammography
US16/525,959 Active US10687776B2 (en) 2004-07-09 2019-07-30 Method for breast screening in fused mammography

Family Applications After (3)

Application Number Title Priority Date Filing Date
US13/694,836 Active US9504436B2 (en) 2004-07-09 2012-11-30 Method for breast screening in fused mammography
US15/359,903 Active US10363010B2 (en) 2004-07-09 2016-11-23 Method for breast screening in fused mammography
US16/525,959 Active US10687776B2 (en) 2004-07-09 2019-07-30 Method for breast screening in fused mammography

Country Status (4)

Country Link
US (4) US8326006B2 (ja)
EP (1) EP1779290A4 (ja)
JP (1) JP2008505704A (ja)
WO (1) WO2006017101A1 (ja)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090100105A1 (en) * 2007-10-12 2009-04-16 3Dr Laboratories, Llc Methods and Systems for Facilitating Image Post-Processing
US9235781B2 (en) 2013-08-09 2016-01-12 Kabushiki Kaisha Toshiba Method of, and apparatus for, landmark location
US9504436B2 (en) * 2004-07-09 2016-11-29 Hologic, Inc. Method for breast screening in fused mammography
US9636073B2 (en) 2012-12-21 2017-05-02 Caperay Medical (Pty) Ltd. Dual-modality mammography

Families Citing this family (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102006021036B4 (de) * 2006-04-28 2010-04-08 Image Diagnost International Gmbh Vorrichtung und Verfahren zur computergestützten Analyse von Mammogrammen
DE102007058968A1 (de) * 2007-12-07 2009-06-18 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. Segmentierung von Mikroverkalkungen in einer Mammographieaufnahme
US8942342B2 (en) 2008-12-29 2015-01-27 Analogic Corporation Multi-modality image acquisition
DE202011110476U1 (de) * 2010-09-09 2014-03-27 Hologic Inc. System zur dynamischen Modifizierung von Aufnahmeparametern während der Bildaufnahme
WO2012063107A1 (en) * 2010-11-08 2012-05-18 Manipal Institute Of Technology Automated tuberculosis screening
WO2012067607A1 (en) 2010-11-16 2012-05-24 Analogic Corporation Multi-modality image acquisition
JP6291813B2 (ja) * 2013-11-29 2018-03-14 コニカミノルタ株式会社 医用画像システム及びプログラム
KR20160032586A (ko) * 2014-09-16 2016-03-24 삼성전자주식회사 관심영역 크기 전이 모델 기반의 컴퓨터 보조 진단 장치 및 방법
CN106203488B (zh) * 2016-07-01 2019-09-13 福州大学 一种基于受限玻尔兹曼机的乳腺图像特征融合方法
JP6397453B2 (ja) * 2016-08-22 2018-09-26 キヤノン株式会社 画像処理装置、画像処理方法およびプログラム
US20180235701A1 (en) * 2017-02-21 2018-08-23 General Electric Company Systems and methods for intervention guidance using pre-operative planning with ultrasound
CN108257674A (zh) * 2018-01-24 2018-07-06 龙马智芯（珠海横琴）科技有限公司 疾病预测方法和装置、设备、计算机可读存储介质
US10796430B2 (en) 2018-04-24 2020-10-06 General Electric Company Multimodality 2D to 3D imaging navigation
KR20200104103A (ko) 2019-02-26 2020-09-03 삼성메디슨 주식회사 초음파 영상과 타 모달리티(modality) 영상을 정합하는 초음파 영상 장치 및 그 동작 방법
WO2021081483A1 (en) 2019-10-25 2021-04-29 DeepHealth, Inc. System and method for analyzing three-dimensional image data
CN114757953B (zh) * 2022-06-15 2022-11-01 深圳瀚维智能医疗科技有限公司 医学超声图像识别方法、设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5627907A (en) 1994-12-01 1997-05-06 University Of Pittsburgh Computerized detection of masses and microcalcifications in digital mammograms
US5832103A (en) 1993-11-29 1998-11-03 Arch Development Corporation Automated method and system for improved computerized detection and classification of massess in mammograms
US6058322A (en) 1997-07-25 2000-05-02 Arch Development Corporation Methods for improving the accuracy in differential diagnosis on radiologic examinations
US6205347B1 (en) * 1998-02-27 2001-03-20 Picker International, Inc. Separate and combined multi-modality diagnostic imaging system
US6282305B1 (en) 1998-06-05 2001-08-28 Arch Development Corporation Method and system for the computerized assessment of breast cancer risk
US20030208116A1 (en) * 2000-06-06 2003-11-06 Zhengrong Liang Computer aided treatment planning and visualization with image registration and fusion
US6650766B1 (en) 1997-08-28 2003-11-18 Qualia Computing, Inc. Method for combining automated detections from medical images with observed detections of a human interpreter

Family Cites Families (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0279177A (ja) * 1988-09-16 1990-03-19 Fuji Photo Film Co Ltd 放射線画像における乳房輪郭検出方法
US6434262B2 (en) * 1993-09-29 2002-08-13 Shih-Ping Wang Computer-aided diagnosis system and method
US5572565A (en) * 1994-12-30 1996-11-05 Philips Electronics North America Corporation Automatic segmentation, skinline and nipple detection in digital mammograms
JPH08263641A (ja) * 1995-01-23 1996-10-11 Fuji Photo Film Co Ltd アイリスフィルターの演算方法
JP3601878B2 (ja) * 1995-07-13 2004-12-15 株式会社東芝 超音波及び核磁気共鳴複合診断装置
JPH1119077A (ja) * 1997-06-30 1999-01-26 Konica Corp 放射線画像における腫瘤影の検出方法及び装置
IL134557A0 (en) 1997-08-28 2001-04-30 Qualia Computing Inc Method and system for automated detection of clustered microcalcifications from digital mammograms
JP3511036B2 (ja) 1997-09-26 2004-03-29 株式会社日本アルファ 排水装置
US6630937B2 (en) * 1997-10-30 2003-10-07 University Of South Florida Workstation interface for use in digital mammography and associated methods
JP2000262511A (ja) * 1999-03-12 2000-09-26 Toshiba Iyo System Engineering Kk 断層撮影装置
US6396940B1 (en) * 1999-05-27 2002-05-28 Litton Systems, Inc. Optical correlator based automated pathologic region of interest selector for integrated 3D ultrasound and digital mammography
JP3768789B2 (ja) 2000-09-07 2006-04-19 アルプス電気株式会社 超音波振動子及びウエット処理用ノズル並びにウエット処理装置
US7103205B2 (en) * 2000-11-24 2006-09-05 U-Systems, Inc. Breast cancer screening with ultrasound image overlays
US7556602B2 (en) * 2000-11-24 2009-07-07 U-Systems, Inc. Breast cancer screening with adjunctive ultrasound mammography
JP2005506140A (ja) * 2001-10-16 2005-03-03 ザ・ユニバーシティー・オブ・シカゴ コンピュータ支援の３次元病変検出方法
US20030149364A1 (en) 2002-02-01 2003-08-07 Ajay Kapur Methods, system and apparatus for digital imaging
FR2835731B1 (fr) * 2002-02-12 2004-10-22 Ge Med Sys Global Tech Co Llc Appareil de mammographie
US6819790B2 (en) * 2002-04-12 2004-11-16 The University Of Chicago Massive training artificial neural network (MTANN) for detecting abnormalities in medical images
US20030194050A1 (en) 2002-04-15 2003-10-16 General Electric Company Multi modality X-ray and nuclear medicine mammography imaging system and method
US7418123B2 (en) * 2002-07-12 2008-08-26 University Of Chicago Automated method and system for computerized image analysis for prognosis
JP2004089212A (ja) * 2002-08-29 2004-03-25 Konica Minolta Holdings Inc 画像処理装置、画像に関する情報の保存方法及びそれを実行させるためのプログラム
US6574304B1 (en) 2002-09-13 2003-06-03 Ge Medical Systems Global Technology Company, Llc Computer aided acquisition of medical images
US6928142B2 (en) * 2002-10-18 2005-08-09 Koninklijke Philips Electronics N.V. Non-invasive plaque detection using combined nuclear medicine and x-ray system
US7236619B2 (en) * 2002-10-31 2007-06-26 University Of Chicago System and method for computer-aided detection and characterization of diffuse lung disease
US7412280B2 (en) * 2003-07-01 2008-08-12 Ge Medical Systems Global Technology Company, Llc Systems and methods for analyzing an abnormality of an object
US8326006B2 (en) * 2004-07-09 2012-12-04 Suri Jasjit S Method for breast screening in fused mammography

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5832103A (en) 1993-11-29 1998-11-03 Arch Development Corporation Automated method and system for improved computerized detection and classification of massess in mammograms
US5627907A (en) 1994-12-01 1997-05-06 University Of Pittsburgh Computerized detection of masses and microcalcifications in digital mammograms
US6058322A (en) 1997-07-25 2000-05-02 Arch Development Corporation Methods for improving the accuracy in differential diagnosis on radiologic examinations
US6650766B1 (en) 1997-08-28 2003-11-18 Qualia Computing, Inc. Method for combining automated detections from medical images with observed detections of a human interpreter
US6205347B1 (en) * 1998-02-27 2001-03-20 Picker International, Inc. Separate and combined multi-modality diagnostic imaging system
US6282305B1 (en) 1998-06-05 2001-08-28 Arch Development Corporation Method and system for the computerized assessment of breast cancer risk
US20030208116A1 (en) * 2000-06-06 2003-11-06 Zhengrong Liang Computer aided treatment planning and visualization with image registration and fusion

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
International Preliminary Report on Patentablity in connection with PCT/US2005/023998.

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9504436B2 (en) * 2004-07-09 2016-11-29 Hologic, Inc. Method for breast screening in fused mammography
US10363010B2 (en) 2004-07-09 2019-07-30 Hologic, Inc. Method for breast screening in fused mammography
US20190350549A1 (en) * 2004-07-09 2019-11-21 Hologic, Inc. Method for breast screening in fused mammography
US10687776B2 (en) * 2004-07-09 2020-06-23 Hologic, Inc. Method for breast screening in fused mammography
US20090100105A1 (en) * 2007-10-12 2009-04-16 3Dr Laboratories, Llc Methods and Systems for Facilitating Image Post-Processing
US9636073B2 (en) 2012-12-21 2017-05-02 Caperay Medical (Pty) Ltd. Dual-modality mammography
US9235781B2 (en) 2013-08-09 2016-01-12 Kabushiki Kaisha Toshiba Method of, and apparatus for, landmark location

Also Published As

Publication number Publication date
US20190350549A1 (en) 2019-11-21
US9504436B2 (en) 2016-11-29
US10687776B2 (en) 2020-06-23
EP1779290A4 (en) 2010-07-07
JP2008505704A (ja) 2008-02-28
US10363010B2 (en) 2019-07-30
WO2006017101A1 (en) 2006-02-16
US20170071563A1 (en) 2017-03-16
US20130251103A1 (en) 2013-09-26
EP1779290A1 (en) 2007-05-02
US20100111379A1 (en) 2010-05-06

Similar Documents

Publication Publication Date Title
US10687776B2 (en) Method for breast screening in fused mammography
Zebari et al. Improved threshold based and trainable fully automated segmentation for breast cancer boundary and pectoral muscle in mammogram images
US7903861B2 (en) Method for classifying breast tissue density using computed image features
AU2005207310B2 (en) System and method for filtering a medical image
US20110257505A1 (en) Atheromatic?: imaging based symptomatic classification and cardiovascular stroke index estimation
Azhari et al. Brain tumor detection and localization in magnetic resonance imaging
JP2009502230A (ja) 医用画像における傷病部位の検知
JP2010207572A (ja) 障害のコンピュータ支援検出
Wang et al. Deep learning for breast region and pectoral muscle segmentation in digital mammography
US20050002548A1 (en) Automatic detection of growing nodules
GB2463906A (en) Identification of medical image objects using local dispersion and Hessian matrix parameters
Yap et al. Fully automatic lesion boundary detection in ultrasound breast images
Zhang et al. Automatic segmentation for breast skin-line
Shah et al. Analysis and identification of renal calculi in computed tomography images
Jaglan et al. Escalate the efficacy of breast tumor detection through magnetic resonance imaging: a framework
Indumathi et al. Effect of co-occurrence filtering for recognizing abnormality from breast thermograms
Abdalla et al. Automatic Segmentation and Detection System for Varicocele Using Ultrasound Images.
Adegoke et al. Overview of medical image segmentation
Sezer et al. Hermite-based texture feature extraction for classification of humeral head in proton density-weighted MR images
Markhande et al. A review on adaptive hierarchy segmentation of bone cancer using neural network in MATLAB
Sungkhun et al. Vertebral body segmentation using aggregate superpixels
Jitender LUNG CANCER DETECTION USING DIGITAL IMAGE PROCESSING AND ARTIFICIAL NEURAL NETWORKS
Prathap et al. A COMPUTER-AIDED PIPELINE DESIGN FOR AUTOMATED CLASSIFICATION OF TUMORS IN LIVER ON COMPUTED TOMOGRAPHY SCAN IMAGES
Rana et al. MRI Image Segmentation by Using DWT for Detection of Brain Tumor
Aruna Kirithika et al. Inspection of Different Segmentation Techniques on FLAIR, T1, T2-Weighted MR Brain Images

Legal Events

Date Code Title Description
AS Assignment

Owner name: GOLDMAN SACHS CREDIT PARTNERS L.P.,CALIFORNIA

Free format text: PATENT SECURITY AGREEMENT;ASSIGNOR:HOLOGIC, INC.;REEL/FRAME:020018/0818

Effective date: 20071022

Owner name: GOLDMAN SACHS CREDIT PARTNERS L.P., CALIFORNIA

Free format text: PATENT SECURITY AGREEMENT;ASSIGNOR:HOLOGIC, INC.;REEL/FRAME:020018/0818

Effective date: 20071022

AS Assignment

Owner name: GOLDMAN SACHS CREDIT PARTNERS L.P., AS COLLATERAL

Free format text: PATENT SECURITY AGREEMENT;ASSIGNOR:HOLOGIC, INC.;REEL/FRAME:021301/0796

Effective date: 20080717

AS Assignment

Owner name: BIOLUCENT, LLC, CALIFORNIA

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

Owner name: CYTYC SURGICAL PRODUCTS LIMITED PARTNERSHIP, MASSA

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

Owner name: THIRD WAVE TECHNOLOGIES, INC., WISCONSIN

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

Owner name: R2 TECHNOLOGY, INC., CALIFORNIA

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

Owner name: HOLOGIC, INC., MASSACHUSETTS

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

Owner name: CYTYC CORPORATION, MASSACHUSETTS

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

Owner name: CYTYC PRENATAL PRODUCTS CORP., MASSACHUSETTS

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

Owner name: CYTYC SURGICAL PRODUCTS III, INC., MASSACHUSETTS

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

Owner name: CYTYC SURGICAL PRODUCTS II LIMITED PARTNERSHIP, MA

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

Owner name: DIRECT RADIOGRAPHY CORP., DELAWARE

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

Owner name: SUROS SURGICAL SYSTEMS, INC., INDIANA

Free format text: TERMINATION OF PATENT SECURITY AGREEMENTS AND RELEASE OF SECURITY INTERESTS;ASSIGNOR:GOLDMAN SACHS CREDIT PARTNERS, L.P., AS COLLATERAL AGENT;REEL/FRAME:024892/0001

Effective date: 20100819

AS Assignment

Owner name: GOLDMAN SACHS BANK USA, NEW YORK

Free format text: SECURITY AGREEMENT;ASSIGNORS:HOLOGIC, INC.;BIOLUCENT, LLC;CYTYC CORPORATION;AND OTHERS;REEL/FRAME:028810/0745

Effective date: 20120801

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: HOLOGIC, INC, MARYLAND

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:FISCHER IMAGING CORPORATION;REEL/FRAME:033402/0970

Effective date: 20050928

AS Assignment

Owner name: CYTYC SURGICAL PRODUCTS, LIMITED PARTNERSHIP, MASSACHUSETTS

Free format text: SECURITY INTEREST RELEASE REEL/FRAME 028810/0745;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:035820/0239

Effective date: 20150529

Owner name: SUROS SURGICAL SYSTEMS, INC., MASSACHUSETTS

Free format text: SECURITY INTEREST RELEASE REEL/FRAME 028810/0745;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:035820/0239

Effective date: 20150529

Owner name: THIRD WAVE TECHNOLOGIES, INC., MASSACHUSETTS

Free format text: SECURITY INTEREST RELEASE REEL/FRAME 028810/0745;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:035820/0239

Effective date: 20150529

Owner name: GEN-PROBE INCORPORATED, MASSACHUSETTS

Free format text: SECURITY INTEREST RELEASE REEL/FRAME 028810/0745;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:035820/0239

Effective date: 20150529

Owner name: CYTYC SURGICAL PRODUCTS, LIMITED PARTNERSHIP, MASS

Free format text: SECURITY INTEREST RELEASE REEL/FRAME 028810/0745;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:035820/0239

Effective date: 20150529

Owner name: HOLOGIC, INC., MASSACHUSETTS

Free format text: SECURITY INTEREST RELEASE REEL/FRAME 028810/0745;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:035820/0239

Effective date: 20150529

Owner name: BIOLUCENT, LLC, MASSACHUSETTS

Free format text: SECURITY INTEREST RELEASE REEL/FRAME 028810/0745;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:035820/0239

Effective date: 20150529

Owner name: CYTYC CORPORATION, MASSACHUSETTS

Free format text: SECURITY INTEREST RELEASE REEL/FRAME 028810/0745;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:035820/0239

Effective date: 20150529

AS Assignment

Owner name: BANK OF AMERICA, N.A., AS COLLATERAL AGENT, NORTH CAROLINA

Free format text: SECURITY AGREEMENT;ASSIGNORS:HOLOGIC, INC.;BIOLUCENT, LLC;CYTYC CORPORATION;AND OTHERS;REEL/FRAME:036307/0199

Effective date: 20150529

Owner name: BANK OF AMERICA, N.A., AS COLLATERAL AGENT, NORTH

Free format text: SECURITY AGREEMENT;ASSIGNORS:HOLOGIC, INC.;BIOLUCENT, LLC;CYTYC CORPORATION;AND OTHERS;REEL/FRAME:036307/0199

Effective date: 20150529

FPAY Fee payment

Year of fee payment: 4

AS Assignment

Owner name: CYTYC SURGICAL PRODUCTS, LIMITED PARTNERSHIP, MASSACHUSETTS

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 035820 FRAME: 0239. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST RELEASE;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:044727/0529

Effective date: 20150529

Owner name: GOLDMAN SACHS BANK USA, NEW YORK

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 028810 FRAME: 0745. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY AGREEMENT;ASSIGNORS:HOLOGIC, INC.;BIOLUCENT, LLC;CYTYC CORPORATION;AND OTHERS;REEL/FRAME:044432/0565

Effective date: 20120801

Owner name: CYTYC SURGICAL PRODUCTS, LIMITED PARTNERSHIP, MASS

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 035820 FRAME: 0239. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST RELEASE;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:044727/0529

Effective date: 20150529

Owner name: HOLOGIC, INC., MASSACHUSETTS

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 035820 FRAME: 0239. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST RELEASE;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:044727/0529

Effective date: 20150529

Owner name: THIRD WAVE TECHNOLOGIES, INC., MASSACHUSETTS

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 035820 FRAME: 0239. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST RELEASE;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:044727/0529

Effective date: 20150529

Owner name: CYTYC CORPORATION, MASSACHUSETTS

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 035820 FRAME: 0239. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST RELEASE;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:044727/0529

Effective date: 20150529

Owner name: BIOLUCENT, LLC, MASSACHUSETTS

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 035820 FRAME: 0239. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST RELEASE;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:044727/0529

Effective date: 20150529

Owner name: GEN-PROBE INCORPORATED, MASSACHUSETTS

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 035820 FRAME: 0239. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST RELEASE;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:044727/0529

Effective date: 20150529

Owner name: SUROS SURGICAL SYSTEMS, INC., MASSACHUSETTS

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT PATENT NO. 8081301 PREVIOUSLY RECORDED AT REEL: 035820 FRAME: 0239. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY INTEREST RELEASE;ASSIGNOR:GOLDMAN SACHS BANK USA, AS COLLATERAL AGENT;REEL/FRAME:044727/0529

Effective date: 20150529

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 8TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1552); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 8

FEPP Fee payment procedure

Free format text: MAINTENANCE FEE REMINDER MAILED (ORIGINAL EVENT CODE: REM.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY